Skip to main content
Your reps self-report deal qualification in the CRM. MEDDPICC scores, SPICED stages, BANT checkboxes — all optimistic by nature. Nobody audits them against what actually happened in the calls and emails. The result: pipeline that looks healthier than it is, deals reaching proposal without an economic buyer identified, forecast accuracy that drifts because the qualification underneath isn’t real. Deal Qualification scores every deal against your methodology from actual signals — calls, emails, CRM, and messaging — delivered where your team works.

​
Data Sources

CategoryRequiredRecommended
CRM✓
Calls✓
Email + Calendar✓
Messaging✓
Starter (required only): a useful audit based on CRM state and call evidence — qualification scores backed by what was said on calls, with the gaps the rep hasn’t surfaced. Full (required + recommended): the same audit, plus important context such as email engagement patterns and any Slack activity from your team or shared customer channels. Same workflow — significantly more signal. See the Customer Context Graph for how each source feeds the brief.

​
Build in Claude or ChatGPT

For teams scoring deals on demand through Claude or ChatGPT. Output appears in your conversation.

​
The Prompt

Open Claude or ChatGPT with the Clearskies MCP connected and paste this (or modify to your needs). Replace the account name with your own. 
Using the Clearskies Context Graph, audit the Acme deal against MEDDPICC.

For each criterion — Metrics, Economic Buyer, Decision Criteria,
Decision Process, Identify Pain, Champion, Competition, Paper Process
— give me:
- A score (Weak / Partial / Strong)
- The evidence from calls, emails, CRM, and Slack
- What's missing or unclear

End with overall qualification health and the gaps that need movement
before close.

Be direct. Don't take rep self-reporting at face value.
Claude or ChatGPT returns an evidence-backed audit, generated from your data and formatted as a chat response. Refine the prompt to fit how your team works deals.

​
Make it yours

  • Add Use SPICED instead of MEDDPICC (or BANT, or your custom criteria) to switch methodologies.
  • Add Compare this audit to what's logged in CRM to surface optimism bias.
  • Add Show me what the rep should focus on this week to chain audit with action.

​
The Skill (Claude)

The clearskies:meddic skill in the Clearskies plugin for Claude runs the same workflow on demand: an evidence-backed audit against your methodology, with scores for every criterion and the gaps that need movement — all from your Context Graph.

​
Trigger phrases

  • “Score [account] against MEDDPICC”
  • “MEDDPICC audit for [account]”
  • “Qualify the [account] deal”

​
Customize it for your team

  • Match the methodology to your team’s framework
  • Set thresholds for Weak / Partial / Strong on each criterion
  • Define which criteria are deal-blockers vs. nice-to-haves
Want this packaged for your team? Reach out and we’ll help you customize the skill to your workflow.

​
The Plugin

Ready to make this part of your team’s workflow? We’ll set up the Clearskies plugin with you — Clearskies workflows, Claude skills, all tailored to how your team works. Book 15 minutes →

​
Next steps

  1. Sign in to Clearskies
  2. Connect your data sources
  3. Get your Clearskies MCP server and try with Claude or ChatGPT